News & Events
Upcoming and Past Events:
- Wednesday 10th March 2020, 2 pm EST: "High-resolution mapping of cells and tissue structures provides a foundation for computational TILs assessment". Mohamed Amgad, member of the TILs Working Group, will be giving a public talk at the Food and Drug Administration (FDA) describing their newest network, NuCLs, and the public release of 220,000 annotations of cell nuclei in breast cancer. Join the Microsoft Teams meeting on Wednesday 10th March, 2 pm EST via this link.
- Click here to access the Webinar on “High-throughput Truthing-project: a collaboration with FDA, the TILs-WG and the Alliance for Digital Pathology on ML-applications for assessment of TILs.”
- Picture 5th International Immuno-Oncology Biomarker Working Group, SABC2018
Catch up on our latest mailings:
- 24th February 2021 - Join our TILs dance: Listen Baby, there ain't no mountain high enough for the TILs
- 11th January 2021 -Happy New Year! Read the first communication for 2021: The TILs and the Laughing Anvil
- 2nd December 2020 - We are ready to leave 2020 behind, read an Update on ongoing TIL projects and why TILs are not such a big deal
- 29th October 2020 - TILs and Machine Learning: FDA, The Alliance and TILs WG Collaboration
- 7 September 2020 - Our WG and the need to put our feet in the right place
- 8th July 2020 - The Science on TILs and the Quest for Meaning in eight items
- 1st April 2020- Our Working Group, COVID19 and The Common Good
Recent publications and other news:
- 19th May, 2020 - The Center for Computational Imaging & Personalized Diagnostics at Case Western Reserve University recently published a paper on the relationship between TILs and Epithelial Ovarian Cancer (EOC). Read it here!
- 12th May, 2020 - TRIPLE WHAMMY! Months of joint effort and global collaborations come together today with the simultaneous publishing of not one, not two, but THREE papers by the TIL Working Group on Nature Partner Journals Breast Cancer
- Pitfalls in assessing stromal tumor infiltrating lymphocytes (sTILs) in breast cancer
- Report on computational assessment of Tumor Infiltrating Lymphocytes from the International Immuno-Oncology Biomarker Working Group
- Application of a risk-management framework for integration of stromal tumor-infiltrating lymphocytes in clinical trials
- Along the development of a Machine Learning Project on TIL-assessment on Breast Cancer HE-slides, the TIL-WG is partnering with PathPresenter. The Faculty of PathPresenter can deliver stunning visual interactive learning experiences in person or online and can connect with other pathologists worldwide (currently 125,000+ users). The freely available 30,000+ slides on the platform make it easy to start today without about having own slides or scanners. Visual information can be found here.
In our project, the PathPresenter platform allows us to store, organize, and view digitized histopathology whole-slide images as well as create collaborative project workflows to manually annotate regions of interest. We are using PathPresenter to combine the effort of several pathologists, engineers, medical students, etc… to create a dataset of manually annotated tissue types and of lymphocytes in whole-slide images of breast cancer tissue samples. The workflow includes a definition of regions of interest, manual annotation of tumour-associated stroma and stromal tumour-infiltrating lymphocytes (sTILs) within those regions. Furthermore, the bulk of breast tumour is also annotated over the entire whole-slide image. Annotations tools available in PathPresenter, as well as features for sharing and interacting with annotations are of vital importance to provide a large amount of high-quality manual annotations, which are required to train modern machine learning tools such as deep neural networks.
For more details, please contact Roberto Salgado -firstname.lastname@example.org- and/or Rajendra Singh - email@example.com
- July 7, 2018 - Our review "Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning" is out! From classical image segmentation to machine learning-based approaches including explainable machine learning that allows for quantification and plausibility checks in biomedical research and diagnostics